Machine Learning Algorithms to Predict Tree-Related Microhabitats using Airborne Laser Scanning

In the last few years, the occurrence and abundance of tree-related microhabitats and habitat trees have gained great attention across Europe as indicators of forest biodiversity. Nevertheless, observing microhabitats in the field requires time and well-trained staff. For this reason, new efficient semiautomatic systems for their identification and mapping on a large scale are necessary. This study aims at predicting microhabitats in a mixed and multi-layered Mediterranean forest using Airborne Laser Scanning data through the implementation of a Machine Learning algorithm. The study focuses on the identification of LiDAR metrics useful for detecting microhabitats according to the recent hierarchical classification system for Tree-related Microhabitats, from single microhabitats to the habitat trees. The results demonstrate that Airborne Laser Scanning point clouds support the prediction of microhabitat abundance. Better prediction capabilities were obtained at a higher hierarchical level and for some of the single microhabitats, such as epiphytic bryophytes, root buttress cavities, and branch holes. Metrics concerned with tree height distribution and crown density are the most important predictors of microhabitats in a multi-layered forest.

[1]  Alexei Botchkarev,et al.  A New Typology Design of Performance Metrics to Measure Errors in Machine Learning Regression Algorithms , 2019, Interdisciplinary Journal of Information, Knowledge, and Management.

[2]  Y. Paillet,et al.  Catalogue of tree microhabitats : Reference field list , 2016 .

[3]  B. Lasserre,et al.  Dynamics of the silver fir (Abies alba Mill.) natural regeneration in a mixed forest in the Central Apennine , 2016 .

[4]  Y. Paillet,et al.  Influence of tree characteristics and forest management on tree microhabitats , 2011 .

[5]  M. Marchetti,et al.  Spatially explicit estimation of forest age by integrating remotely sensed data and inverse yield modeling techniques , 2016 .

[6]  I. Király,et al.  Factors influencing epiphytic bryophyte and lichen species richness at different spatial scales in managed temperate forests , 2012, Biodiversity and Conservation.

[7]  R. Tognetti,et al.  Large-scale estimation of xylem phenology in black spruce through remote sensing , 2017 .

[8]  Bogdan M. Strimbu,et al.  Bayesian and Classical Machine Learning Methods: A Comparison for Tree Species Classification with LiDAR Waveform Signatures , 2017, Remote. Sens..

[9]  F. Harrell,et al.  Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors , 2005 .

[10]  P. Corona,et al.  Large-scale two-phase estimation of wood production by poplar plantations exploiting Sentinel-2 data as auxiliary information , 2020 .

[11]  Nicholas C. Coops,et al.  Demonstrating the transferability of forest inventory attribute models derived using airborne laser scanning data , 2019, Remote Sensing of Environment.

[12]  B. Lasserre,et al.  First mapping of the main high conservation value forests (HCVFs) at national scale: The case of Italy , 2016 .

[13]  Ellen Poliakoff,et al.  Machine learning algorithm validation with a limited sample size , 2019, PloS one.

[14]  Tomislav Hengl,et al.  Global mapping of potential natural vegetation: an assessment of machine learning algorithms for estimating land potential , 2018, PeerJ.

[15]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[16]  M. Di Febbraro,et al.  Using macroecological constraints on spatial biodiversity predictions under climate change: the modelling method matters , 2018, Ecological Modelling.

[17]  B. Lasserre,et al.  Biodiversity conservation and wood production in a Natura 2000 Mediterranean forest. A trade-off evaluation focused on the occurrence of microhabitats , 2019, iForest - Biogeosciences and Forestry.

[18]  G. Matteucci,et al.  Forest certification map of Europe , 2018, iForest - Biogeosciences and Forestry.

[19]  Piermaria Corona,et al.  Integrating terrestrial and airborne laser scanning for the assessment of single-tree attributes in Mediterranean forest stands , 2018 .

[20]  Thibault Lachat,et al.  Tree related microhabitats in temperate and Mediterranean European forests: A hierarchical typology for inventory standardization , 2018 .

[21]  Michele Dalponte,et al.  Airborne laser scanning of forest resources: An overview of research in Italy as a commentary case study , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[22]  Marco Marchetti,et al.  Copernicus high-resolution layers for land cover classification in Italy , 2016 .

[23]  Gherardo Chirici,et al.  Combination of optical and LiDAR satellite imagery with forest inventory data to improve wall-to-wall assessment of growing stock in Italy , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[24]  Terje Gobakken,et al.  A new approach with DTM-independent metrics for forest growing stock prediction using UAV photogrammetric data , 2018, Remote Sensing of Environment.

[25]  C. Kerbiriou,et al.  Which factors influence the occurrence and density of tree microhabitats in Mediterranean oak forests , 2013 .

[26]  R. Tognetti,et al.  Community fingerprinting reveals increasing wood-inhabiting fungal diversity in unmanaged Mediterranean forests , 2018 .

[27]  Y. Paillet,et al.  Habitat trees: key elements for forest biodiversity , 2013 .

[28]  Bernhard Wolfslehner,et al.  Evaluating the implementation of the Pan-European Criteria and indicators for sustainable forest management – A SWOT analysis , 2016 .

[29]  G. Tabacchi,et al.  L’Inventario Nazionale delle Foreste e dei serbatoi forestali di Carbonio INFC 2005. Secondo inventario forestale nazionale italiano. Metodi e risultati. , 2011 .

[30]  G. Mugnozza,et al.  Social perception of forest multifunctionality in southern Italy: The case of Calabria Region , 2016 .

[31]  Lars T. Waser,et al.  Identifying Tree-Related Microhabitats in TLS Point Clouds Using Machine Learning , 2018, Remote. Sens..

[32]  Susanne Winter,et al.  Microhabitats in lowland beech forests as monitoring tool for nature conservation , 2008 .

[33]  Emanuele Santi,et al.  The potential of multifrequency SAR images for estimating forest biomass in Mediterranean areas , 2017 .

[34]  R. Tognetti,et al.  Relationships between stand structural attributes and saproxylic beetle abundance in a Mediterranean broadleaved mixed forest , 2019, Forest Ecology and Management.

[35]  Lucio Barabesi,et al.  Properties of design-based estimation under stratified spatial sampling with application to canopy coverage estimation , 2012, 1203.4065.

[36]  S. Puliti,et al.  Assessment of UAV photogrammetric DTM-independent variables for modelling and mapping forest structural indices in mixed temperate forests , 2020 .

[37]  M. Marchetti,et al.  Mapping forest ecosystem functions for landscape planning in a mountain Natura2000 site, Central Italy1 , 2015 .

[38]  F. Krumm,et al.  Reconciling the Tradeoff between Economic and Ecological Objectives in Habitat-Tree Selection: A Comparison between Students, Foresters, and Forestry Trainers , 2018, Forest Science.

[39]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[40]  M. Marchetti,et al.  Implementing Criteria and Indicators for Sustainable Forest Management in a Decentralized Setting: Italy as a Case Study , 2016 .

[41]  R. Tognetti,et al.  Deadwood Occurrence and Forest Structure as Indicators of Old-Growth Forest Conditions in Mediterranean Mountainous Ecosystems , 2012 .

[42]  R. Tognetti,et al.  Assessment of potential bioenergy from coppice forests trough the integration of remote sensing and field surveys. , 2011 .

[43]  J. Bauhus,et al.  Predictors of Microhabitat Frequency and Diversity in Mixed Mountain Forests in South-Western Germany , 2018 .

[44]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[45]  Harald Schaich,et al.  Land ownership affects diversity and abundance of tree microhabitats in deciduous temperate forests , 2016 .

[46]  Gherardo Chirici,et al.  Comparing echo-based and canopy height model-based metrics for enhancing estimation of forest aboveground biomass in a model-assisted framework , 2016 .

[47]  J. Bauhus,et al.  Predicting abundance and diversity of tree-related microhabitats in Central European montane forests from common forest attributes , 2019, Forest Ecology and Management.

[48]  B. Lasserre,et al.  Forest Inventory Attribute Prediction Using Lightweight Aerial Scanner Data in a Selected Type of Multilayered Deciduous Forest , 2016 .

[49]  M. Marchetti,et al.  Application of indicators network analysis to support local forest management plan development: a case study in Molise, Italy , 2012 .

[50]  R. McRoberts,et al.  Estimating and mapping forest structural diversity using airborne laser scanning data , 2015 .

[51]  R. Mosandl,et al.  Formerly managed forest reserves complement integrative management for biodiversity conservation in temperate European forests , 2020 .

[52]  Gherardo Chirici,et al.  Assessing Forest Naturalness , 2012 .

[53]  Antoine Guisan,et al.  Overcoming limitations of modelling rare species by using ensembles of small models , 2015 .

[54]  Y. Paillet,et al.  Biodiversity Differences between Managed and Unmanaged Forests: Meta‐Analysis of Species Richness in Europe , 2010, Conservation biology : the journal of the Society for Conservation Biology.

[55]  Alexa K. Michel,et al.  Tree microhabitat structures as indicators of biodiversity in Douglas-fir forests of different stand ages and management histories in the Pacific Northwest, U.S.A. , 2009 .

[56]  Y. Paillet,et al.  Nothing else matters? Tree diameter and living status have more effects than biogeoclimatic context on microhabitat number and occurrence: An analysis in French forest reserves , 2019, PloS one.